Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms or expressions related to mathematical or computational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical/scientific notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.61
    KommentareTeilen
    -0.59
     desmotivaciones
    -0.59
    RegressionTest
    -0.58
     MainAxisSize
    -0.57
     noDo
    -0.57
     صوتيه
    -0.57
     greateſt
    -0.56
    enterOuterAlt
    -0.56
     myſelf
    -0.55
    POSITIVE LOGITS
    白菜
    0.35
    ControllerTest
    0.34
    TagMode
    0.34
    躾
    0.33
    Segue
    0.33
    ina
    0.32
    KURZBESCHREIBUNG
    0.32
    yet
    0.32
    bund
    0.31
     réf
    0.31
    Act Density 1.083%

    No Known Activations